As an emerging technology, WiFi sensing has garnered widespread attention in recent years. However, due to limitations in WiFi bandwidth and hardware capacity, multi-target sensing with WiFi remains an unresolved issue. In this paper, we presentSlingShot, a first-of-its-kind approach for multi-target WiFi sensing enabled by metasurface.SlingShotexploits a metasurface's ability of beam scanning to periodically scan among targets in a high frequency, so their sensing signals can be separated in the time domain. However, the WiFi-initiated and the metasurface-initiated signals will interfere with each other, which could significantly degrade the sensing accuracy. Moreover, the WiFi devices and the metasurface operate in a distributed manner, so the inherent clock offset and clock drift among them make it difficult to accurately separate the sensing signals of the targets. To address the above challenges,SlingShotleverages the metasurface's ability of phase shifting to cancel interfering signals and designs a passive clock synchronization scheme to synchronize the metasurface and WiFi devices. We implementSlingShotand evaluate it under various settings. Results show thatSlingShotcan sense up to 8 targets. Respectively compared to the state-of-the-art methods,SlingShothas 6.75 % higher mean accuracy in activity recognition and 58.34 % lower mean error in respiration monitoring.

3D Gaussian Splatting (3DGS) has become horsepower in high-quality, real-time rendering for novel view synthesis of 3D scenes. However, existing methods focus primarily on geometric and appearance modeling, lacking deeper scene understanding while also incurring high training costs that complicate the originally streamlined differentiable rendering pipeline. To this end, we propose VoteSplat, a novel 3D scene understanding framework that integrates Hough voting with 3DGS. Specifically, Segment Anything Model (SAM) is utilized for instance segmentation, extracting objects, and generating 2D vote maps. We then embed spatial offset vectors into Gaussian primitives. These offsets construct 3D spatial votes by associating them with 2D image votes, while depth distortion constraints refine localization along the depth axis. For open-vocabulary object localization, VoteSplat maps 2D image semantics to 3D point clouds via voting points, reducing training costs associated with high-dimensional CLIP features while preserving semantic unambiguity. Extensive experiments demonstrate effectiveness of VoteSplat in open-vocabulary 3D instance localization, 3D point cloud understanding, click-based 3D object localization, hierarchical segmentation, and ablation studies. Our code is available at https://sy-ja.github.io/votesplat/

Wi-Fi human sensing has attracted numerous research studies over the past decade. The rapid advancement of machine learning technology further boosts the development of Wi-Fi human sensing. However, current Wi-Fi human sensing suffers from the “data scarcity” problem: all the existing proposals require collecting a large amount of human-based datasets to train the sensing models, which is laborintensive and may raise ethical concerns in certain scenarios. This obstacle seriously restricts the size, quality, and diversity of available datasets, thereby affecting the sensing performance in terms of accuracy and cross-domain applicability. In order to solve this problem, we in this paper propose Metasurface-Assisted Sample Synthesis (MASS), a novel approach to synthesize high-fidelity Wi-Fi sensing samples that effectively capture both the essential features of human motion and environment-specific multipath characteristics without requiring human involvement. The evaluation results show that MASS is effective in boosting machine learning performance, improving classification accuracy by 18%, and enhancing the cross-domain sensing accuracy by 22%. We further analyze inherent synthesis distortions stemming from hardware limitations and introduce a mitigation technique, which significantly enhances data fidelity, achieving 91.8% accuracy even when training exclusively on synthesized samples. These findings underscore the potential of MASS to facilitate the creation of high-quality, diverse datasets with minimal human involvement and associated labor costs.

Abstract As an amalgamation of landscape design and ichthyology, aquascape endeavors to create visually captivating aquatic environments imbued with artistic allure. Traditional methodologies in aquascape, governed by rigid principles such as composition and color coordination, may inadvertently curtail the aesthetic potential of the landscapes. In this paper, we propose Aquascape Generation based on Stable Diffusion Models (AG‐SDM), prioritizing aesthetic principles and color coordination to offer guiding principles for real artists in Aquascape creation. We meticulously curated and annotated three aquascape datasets with varying aspect ratios to accommodate diverse landscape design requirements regarding dimensions and proportions. Leveraging the Fréchet Inception Distance (FID) metric, we trained AGFID for quality assessment. Extensive experiments validate that our AG‐SDM excels in generating hyper‐realistic underwater landscape images, closely resembling real flora, and achieves state‐of‐the‐art performance in aquascape image generation.

Collaborative perception offers a promising solution to overcome challenges such as occlusion and long-range data processing. However, limited sensor accuracy leads to noisy poses that misalign observations among vehicles. To address this problem, we propose the FeaCo, which achieves robust Feature-level Consensus among collaborating agents in noisy pose conditions without additional training. We design an efficient Pose-error Rectification Module (PRM) to align derived feature maps from different vehicles, reducing the adverse effect of noisy pose and bandwidth requirements. We also provide an effective multi-scale Cross-level Attention Module (CAM) to enhance information aggregation and interaction between various scales. Our FeaCo outperforms all other localization rectification methods, as validated on both the collaborative perception simulation dataset OPV2V and real-world dataset V2V4Real, reducing heading error and enhancing localization accuracy across various error levels. Our code is available at: https://github.com/jmgu0212/FeaCo.git.

Neural Radiance Fields (NeRF) is a novel implicit 3D reconstruction method that shows immense potential and has been gaining increasing attention. It enables the reconstruction of 3D scenes solely from a set of photographs. However, its real-time rendering capability, especially for interactive real-time rendering of large-scale scenes, still has significant limitations. To address these challenges, in this paper, we propose a novel neural rendering system called UE4-NeRF, specifically designed for real-time rendering of large-scale scenes. We partitioned each large scene into different sub-NeRFs. In order to represent the partitioned independent scene, we initialize polygonal meshes by constructing multiple regular octahedra within the scene and the vertices of the polygonal faces are continuously optimized during the training process. Drawing inspiration from Level of Detail (LOD) techniques, we trained meshes of varying levels of detail for different observation levels. Our approach combines with the rasterization pipeline in Unreal Engine 4 (UE4), achieving real-time rendering of large-scale scenes at 4K resolution with a frame rate of up to 43 FPS. Rendering within UE4 also facilitates scene editing in subsequent stages. Furthermore, through experiments, we have demonstrated that our method achieves rendering quality comparable to state-of-the-art approaches. Project page: https://jamchaos.github.io/UE4-NeRF/.

Simultaneous orthophoto stitching during the flight of Unmanned Aerial Vehicles (UAV) can greatly promote the practicability and instantaneity of diverse applications such as emergency disaster rescue, digital agriculture, and cadastral survey, which is of remarkable interest in aerial photogrammetry. However, the inaccurately estimated camera poses and the intuitive fusion strategy of existing methods lead to misalignment and distortion artifacts in orthophoto mosaics. To address these issues, we propose a Georeferenced Real-time Orthophoto Stitching method (GeoROS), which can achieve efficient and accurate camera pose estimation through exploiting geolocation information in monocular visual simultaneous localization and mapping (SLAM) and fuse transformed images via orthogonality-preserving criterion. Specifically, in the SLAM process, georeferenced tracking is employed to acquire high-quality initial camera poses with a geolocation based motion model and facilitate non-linear pose optimization. Meanwhile, we design a georeferenced mapping scheme by introducing robust geolocation constraints in joint optimization of camera poses and the position of landmarks. Finally, aerial images warped with localized cameras are fused by considering both the orthogonality of camera orientation relative to the ground plane and the pixel centrality to fulfill global orthorectification. Besides, we construct two datasets with global navigation satellite system (GNSS) information of different scenarios and validate the superiority of our GeoROS method compared with state-of-the-art methods in accuracy and efficiency.